1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440 | /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
* This file is part of the LibreOffice project.
*
* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/.
*
* This file incorporates work covered by the following license notice:
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed
* with this work for additional information regarding copyright
* ownership. The ASF licenses this file to you under the Apache
* License, Version 2.0 (the "License"); you may not use this file
* except in compliance with the License. You may obtain a copy of
* the License at http://www.apache.org/licenses/LICENSE-2.0 .
*/
#include <config_locales.h>
#include <sal/log.hxx>
#include <lrl_include.hxx>
#include <rtl/ustrbuf.hxx>
#include <i18nlangtag/languagetag.hxx>
#include <i18nlangtag/languagetagicu.hxx>
#include <collator_unicode.hxx>
#include <localedata.hxx>
#include <com/sun/star/i18n/CollatorOptions.hpp>
#include <cppuhelper/supportsservice.hxx>
using namespace ::com::sun::star;
using namespace ::com::sun::star::i18n;
using namespace ::com::sun::star::lang;
using namespace ::com::sun::star::uno;
namespace i18npool {
static const char implementationName[] = "com.sun.star.i18n.Collator_Unicode";
Collator_Unicode::Collator_Unicode()
{
collator = nullptr;
uca_base = nullptr;
#ifndef DISABLE_DYNLOADING
hModule = nullptr;
#endif
}
Collator_Unicode::~Collator_Unicode()
{
collator.reset();
uca_base.reset();
#ifndef DISABLE_DYNLOADING
if (hModule) osl_unloadModule(hModule);
#endif
}
#ifdef DISABLE_DYNLOADING
extern "C" {
// For DISABLE_DYNLOADING the generated functions have names that
// start with get_collator_data_ to avoid clashing with a few
// functions in the generated libindex_data that are called just
// get_zh_pinyin for instance.
const sal_uInt8* get_collator_data_ca_charset();
const sal_uInt8* get_collator_data_cu_charset();
const sal_uInt8* get_collator_data_dz_charset();
const sal_uInt8* get_collator_data_hu_charset();
const sal_uInt8* get_collator_data_ja_charset();
const sal_uInt8* get_collator_data_ja_phonetic_alphanumeric_first();
const sal_uInt8* get_collator_data_ja_phonetic_alphanumeric_last();
const sal_uInt8* get_collator_data_ko_charset();
const sal_uInt8* get_collator_data_ku_alphanumeric();
const sal_uInt8* get_collator_data_ln_charset();
const sal_uInt8* get_collator_data_my_dictionary();
const sal_uInt8* get_collator_data_ne_charset();
const sal_uInt8* get_collator_data_sid_charset();
const sal_uInt8* get_collator_data_zh_TW_charset();
const sal_uInt8* get_collator_data_zh_TW_radical();
const sal_uInt8* get_collator_data_zh_TW_stroke();
const sal_uInt8* get_collator_data_zh_charset();
const sal_uInt8* get_collator_data_zh_pinyin();
const sal_uInt8* get_collator_data_zh_radical();
const sal_uInt8* get_collator_data_zh_stroke();
const sal_uInt8* get_collator_data_zh_zhuyin();
size_t get_collator_data_ca_charset_length();
size_t get_collator_data_cu_charset_length();
size_t get_collator_data_dz_charset_length();
size_t get_collator_data_hu_charset_length();
size_t get_collator_data_ja_charset_length();
size_t get_collator_data_ja_phonetic_alphanumeric_first_length();
size_t get_collator_data_ja_phonetic_alphanumeric_last_length();
size_t get_collator_data_ko_charset_length();
size_t get_collator_data_ku_alphanumeric_length();
size_t get_collator_data_ln_charset_length();
size_t get_collator_data_my_dictionary_length();
size_t get_collator_data_ne_charset_length();
size_t get_collator_data_sid_charset_length();
size_t get_collator_data_zh_TW_charset_length();
size_t get_collator_data_zh_TW_radical_length();
size_t get_collator_data_zh_TW_stroke_length();
size_t get_collator_data_zh_charset_length();
size_t get_collator_data_zh_pinyin_length();
size_t get_collator_data_zh_radical_length();
size_t get_collator_data_zh_stroke_length();
size_t get_collator_data_zh_zhuyin_length();
}
#endif
sal_Int32 SAL_CALL
Collator_Unicode::compareSubstring( const OUString& str1, sal_Int32 off1, sal_Int32 len1,
const OUString& str2, sal_Int32 off2, sal_Int32 len2)
{
return collator->compare(reinterpret_cast<const UChar *>(str1.getStr()) + off1, len1, reinterpret_cast<const UChar *>(str2.getStr()) + off2, len2);
}
sal_Int32 SAL_CALL
Collator_Unicode::compareString( const OUString& str1, const OUString& str2)
{
return collator->compare(reinterpret_cast<const UChar *>(str1.getStr()), str1.getLength(),
reinterpret_cast<const UChar *>(str2.getStr()), str2.getLength());
}
#ifndef DISABLE_DYNLOADING
extern "C" { static void thisModule() {} }
#endif
sal_Int32 SAL_CALL
Collator_Unicode::loadCollatorAlgorithm(const OUString& rAlgorithm, const lang::Locale& rLocale, sal_Int32 options)
{
if (!collator) {
UErrorCode status = U_ZERO_ERROR;
OUString rule = LocaleDataImpl::get()->getCollatorRuleByAlgorithm(rLocale, rAlgorithm);
if (!rule.isEmpty()) {
collator.reset( new icu::RuleBasedCollator(reinterpret_cast<const UChar *>(rule.getStr()), status) );
if (! U_SUCCESS(status)) {
OUString message = "icu::RuleBasedCollator ctor failed: " + OUString::createFromAscii(u_errorName(status));
SAL_WARN("i18npool", message);
throw RuntimeException(message);
}
}
if (!collator && OUString(LOCAL_RULE_LANGS).indexOf(rLocale.Language) >= 0) {
const sal_uInt8* (*func)() = nullptr;<--- Assignment 'func=nullptr', assigned value is 0
size_t (*funclen)() = nullptr;
#ifndef DISABLE_DYNLOADING
OUStringBuffer aBuf;
#ifdef SAL_DLLPREFIX
aBuf.append(SAL_DLLPREFIX);<--- Skipping configuration 'SAL_DLLPREFIX' since the value of 'SAL_DLLPREFIX' is unknown. Use -D if you want to check it. You can use -U to skip it explicitly.
#endif
aBuf.append( "collator_data" ).append( SAL_DLLEXTENSION );
hModule = osl_loadModuleRelative( &thisModule, aBuf.makeStringAndClear().pData, SAL_LOADMODULE_DEFAULT );
if (hModule) {
aBuf.append("get_").append(rLocale.Language).append("_");
if ( rLocale.Language == "zh" ) {
OUString func_base = aBuf.makeStringAndClear();
if (OUString("TW HK MO").indexOf(rLocale.Country) >= 0)
{
func = reinterpret_cast<const sal_uInt8* (*)()>(osl_getFunctionSymbol(hModule,
OUString(func_base + "TW_" + rAlgorithm).pData));
funclen = reinterpret_cast<size_t (*)()>(osl_getFunctionSymbol(hModule,
OUString(func_base + "TW_" + rAlgorithm + "_length").pData));
}
if (!func)
{
func = reinterpret_cast<const sal_uInt8* (*)()>(osl_getFunctionSymbol(
hModule, OUString(func_base + rAlgorithm).pData));
funclen = reinterpret_cast<size_t (*)()>(osl_getFunctionSymbol(
hModule, OUString(func_base + rAlgorithm + "_length").pData));
}
} else {
if ( rLocale.Language == "ja" ) {
// replace algorithm name to implementation name.
if (rAlgorithm == "phonetic (alphanumeric first)")
aBuf.append("phonetic_alphanumeric_first");
else if (rAlgorithm == "phonetic (alphanumeric last)")
aBuf.append("phonetic_alphanumeric_last");
else
aBuf.append(rAlgorithm);
} else {
aBuf.append(rAlgorithm);
}
OUString func_base = aBuf.makeStringAndClear();
OUString funclen_base = func_base + "_length";
func = reinterpret_cast<const sal_uInt8* (*)()>(osl_getFunctionSymbol(hModule, func_base.pData));
funclen = reinterpret_cast<size_t (*)()>(osl_getFunctionSymbol(hModule, funclen_base.pData));
}
}
#else
if (false) {
;
#if WITH_LOCALE_ALL || WITH_LOCALE_ca
} else if ( rLocale.Language == "ca" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ca_charset;
funclen = get_collator_data_ca_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_cu
} else if ( rLocale.Language == "cu" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_cu_charset;
funclen = get_collator_data_cu_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_dz
} else if ( rLocale.Language == "dz" || rLocale.Language == "bo" ) {
// 'bo' Tibetan uses the same collation rules as 'dz' Dzongkha
if ( rAlgorithm == "charset" )
{
func = get_collator_data_dz_charset;
funclen = get_collator_data_dz_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_hu
} else if ( rLocale.Language == "hu" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_hu_charset;
funclen = get_collator_data_hu_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ja
} else if ( rLocale.Language == "ja" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ja_charset;
funclen = get_collator_data_ja_charset_length;
}
else if ( rAlgorithm == "phonetic (alphanumeric first)" )
{
func = get_collator_data_ja_phonetic_alphanumeric_first;
funclen = get_collator_data_ja_phonetic_alphanumeric_first_length;
}
else if ( rAlgorithm == "phonetic (alphanumeric last)" )
{
func = get_collator_data_ja_phonetic_alphanumeric_last;
funclen = get_collator_data_ja_phonetic_alphanumeric_last_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ko
#if (U_ICU_VERSION_MAJOR_NUM < 53)
} else if ( rLocale.Language == "ko" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ko_charset;
funclen = get_collator_data_ko_charset_length;
}
#endif
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ku
} else if ( rLocale.Language == "ku" ) {
if ( rAlgorithm == "alphanumeric" )
{
func = get_collator_data_ku_alphanumeric;
funclen = get_collator_data_ku_alphanumeric_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ln
} else if ( rLocale.Language == "ln" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ln_charset;
funclen = get_collator_data_ln_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_my
} else if ( rLocale.Language == "my" ) {
if ( rAlgorithm == "dictionary" )
{
func = get_collator_data_my_dictionary;
funclen = get_collator_data_my_dictionary_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_ne
} else if ( rLocale.Language == "ne" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_ne_charset;
funclen = get_collator_data_ne_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_sid
} else if ( rLocale.Language == "sid" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_sid_charset;
funclen = get_collator_data_sid_charset_length;
}
#endif
#if WITH_LOCALE_ALL || WITH_LOCALE_zh
} else if ( rLocale.Language == "zh" && (rLocale.Country == "TW" || rLocale.Country == "HK" || rLocale.Country == "MO") ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_zh_TW_charset;
funclen = get_collator_data_zh_TW_charset_length;
}
else if ( rAlgorithm == "radical" )
{
func = get_collator_data_zh_TW_radical;
funclen = get_collator_data_zh_TW_radical_length;
}
else if ( rAlgorithm == "stroke" )
{
func = get_collator_data_zh_TW_stroke;
funclen = get_collator_data_zh_TW_stroke_length;
}
} else if ( rLocale.Language == "zh" ) {
if ( rAlgorithm == "charset" )
{
func = get_collator_data_zh_charset;
funclen = get_collator_data_zh_charset_length;
}
else if ( rAlgorithm == "pinyin" )
{
func = get_collator_data_zh_pinyin;
funclen = get_collator_data_zh_pinyin_length;
}
else if ( rAlgorithm == "radical" )
{
func = get_collator_data_zh_radical;
funclen = get_collator_data_zh_radical_length;
}
else if ( rAlgorithm == "stroke" )
{
func = get_collator_data_zh_stroke;
funclen = get_collator_data_zh_stroke_length;
}
else if ( rAlgorithm == "zhuyin" )
{
func = get_collator_data_zh_zhuyin;
funclen = get_collator_data_zh_zhuyin_length;
}
#endif
}
#endif // DISABLE_DYNLOADING
if (func && funclen) {<--- Condition 'func' is always false
const sal_uInt8* ruleImage=func();
size_t ruleImageSize = funclen();
#if (U_ICU_VERSION_MAJOR_NUM == 4) && (U_ICU_VERSION_MINOR_NUM <= 2)
uca_base = new icu::RuleBasedCollator(static_cast<UChar*>(NULL), status);
#else
// Not only changed ICU 53.1 the API behavior that a negative
// length (ruleImageSize) now leads to failure, but also that
// the base RuleBasedCollator passed as uca_base here needs to
// have a base->tailoring == CollationRoot::getRoot() otherwise
// the init bails out as well, as it does for the previously
// used "empty" RuleBasedCollator.
// The default collator of the en-US locale would also fulfill
// the requirement. The collator of the actual locale or the
// NULL (default) locale does not.
uca_base.reset( static_cast<icu::RuleBasedCollator*>(icu::Collator::createInstance(
icu::Locale::getRoot(), status)) );
#endif
if (! U_SUCCESS(status)) {
OUString message = "icu::Collator::createInstance() failed: " + OUString::createFromAscii(u_errorName(status));
SAL_WARN("i18npool", message);
throw RuntimeException(message);
}
collator.reset( new icu::RuleBasedCollator(
reinterpret_cast<const uint8_t*>(ruleImage), ruleImageSize, uca_base.get(), status) );
if (! U_SUCCESS(status)) {
OUString message = "icu::RuleBasedCollator ctor failed: " + OUString::createFromAscii(u_errorName(status));
SAL_WARN("i18npool", message);
throw RuntimeException(message);
}
}
}
if (!collator) {
/** ICU collators are loaded using a locale only.
ICU uses Variant as collation algorithm name (like de__PHONEBOOK
locale), note the empty territory (Country) designator in this special
case here.
But sometimes the mapping fails, eg for German (from Germany) phonebook, we'll have "de_DE_PHONEBOOK"
this one won't be remapping to collation keyword specifiers "de@collation=phonebook"
See http://userguide.icu-project.org/locale#TOC-Variant-code, Level 2 canonicalization, 8.
So let variant empty and use the fourth arg of icuLocale "keywords"
See LanguageTagIcu::getIcuLocale from i18nlangtag/source/languagetag/languagetagicu.cxx
The icu::Locale constructor changes the algorithm name to
uppercase itself, so we don't have to bother with that.
*/
icu::Locale icuLocale( LanguageTagIcu::getIcuLocale( LanguageTag( rLocale),
"", rAlgorithm.isEmpty() ? OUString("") : "collation=" + rAlgorithm));
// load ICU collator
collator.reset( static_cast<icu::RuleBasedCollator*>( icu::Collator::createInstance(icuLocale, status) ) );
if (! U_SUCCESS(status)) {
OUString message = "icu::Collator::createInstance() failed: " + OUString::createFromAscii(u_errorName(status));
SAL_WARN("i18npool", message);
throw RuntimeException(message);
}
}
}
if (options & CollatorOptions::CollatorOptions_IGNORE_CASE_ACCENT)
collator->setStrength(icu::Collator::PRIMARY);
else if (options & CollatorOptions::CollatorOptions_IGNORE_CASE)
collator->setStrength(icu::Collator::SECONDARY);
else
collator->setStrength(icu::Collator::TERTIARY);
return 0;
}
OUString SAL_CALL
Collator_Unicode::getImplementationName()
{
return implementationName;
}
sal_Bool SAL_CALL
Collator_Unicode::supportsService(const OUString& rServiceName)
{
return cppu::supportsService(this, rServiceName);
}
Sequence< OUString > SAL_CALL
Collator_Unicode::getSupportedServiceNames()
{
Sequence< OUString > aRet { OUString(implementationName) };
return aRet;
}
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|